{"type":"ScholarlyArticle","title":"Learning Interpretable Relational Structures of Hinge-loss Markov Random Fields","authors":[{"name":"Yue Zhang","slug":"yue-zhang","given":"Yue","family":"Zhang","affiliation":"SUNY Binghamton"},{"name":"Arti Ramesh","slug":"arti-ramesh","given":"Arti","family":"Ramesh","affiliation":"SUNY Binghamton"}],"abstract":"Statistical relational models such as Markov logic networks (MLNs) and hinge-loss Markov random fields (HL-MRFs) are specified using templated weighted first-order logic clauses, leading to the creation of complex, yet easy to encode models that effectively combine uncertainty and logic. Learning the structure of these models from data reduces the human effort of identifying the right structures. In this work, we present an asynchronous deep reinforcement learning algorithm to automatically learn HL-MRF clause structures. Our algorithm possesses the ability to learn semantically meaningful structures that appeal to human intuition and understanding, while simultaneously being able to learn structures from data, thus learning structures that have both the desirable qualities of interpretability and good prediction performance. The asynchronous nature of our algorithm further provides the ability to learn diverse structures via exploration, while remaining scalable. We demonstrate the ability of the models to learn semantically meaningful structures that also achieve better prediction performance when compared with a greedy search algorithm, a path-based algorithm, and manually defined clauses on two computational social science applications: i) modeling recovery in alcohol use disorder, and ii) detecting bullying.","doi":"10.24963/ijcai.2019/838","url":"https://ijcai.org/proceedings/2019/838","pdf":"https://ijcai.org/proceedings/2019/0838.pdf","markdown":"https://ijcai.org/proceedings/2019/838.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/838","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"AI for Improving Human Well-being","track":"AI for Improving Human Well-being","number":838,"pages":{"first":6050,"last":6056},"keywords":["Special Track on AI for Improving Human-Well Being: AI benefits to society AI applications (Special Track on AI and Human Wellbeing)","Special Track on AI for Improving Human-Well Being: AI applications for Improving Human-Well Being (Special Track on AI and Human Wellbeing)"],"videos":[],"references":[{"position":1,"raw":"[Angelino et al., 2018] Elaine Angelino, Nicholas Larus- Stone, Daniel Alabi, Margo Seltzer, and Cynthia Rudin. Learning certifiably optimal rule lists for categorical data. JMLR, pages 1-78, 2018.","title":"Learning certifiably optimal rule lists for categorical data","authors":"Elaine Angelino, Nicholas Larus-Stone, Daniel Alabi, Margo Seltzer, Cynthia Rudin","year":"2018","venue":"JMLR","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bach et al., 2017] Stephen H Bach, Matthias Broecheler, Bert Huang, and Lise Getoor. Hinge-loss Markov random fields and probabilistic soft logic. JMLR, 18(109):1-67, 2017.","title":"Hinge-loss Markov random fields and probabilistic soft logic","authors":"Matthias Stephen H Bach, Bert Broecheler, Lise Huang, Getoor","year":"2017","venue":"JMLR","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Biba et al., 2008] Marenglen Biba, Stefano Ferilli, and Flo- riana Esposito. Discriminative structure learning of Markov logic networks. In ILP, 2008.","title":"Discriminative structure learning of Markov logic networks","authors":"Biba","year":"2008","venue":"ILP","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Embar et al., 2018] Varun Embar, Dhanya Sridhar, Gol- noosh Farnadi, and Lise Getoor. Scalable structure learn- ing for probabilistic soft logic. IJCAI StarAI Workshop, 2018.","title":"Scalable structure learning for probabilistic soft logic","authors":"Varun Embar, Dhanya Sridhar, Golnoosh Farnadi, Lise Getoor","year":"2018","venue":"IJCAI StarAI Workshop","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Haarnoja et al., 2017] Tuomas Haarnoja, Haoran Tang, Pieter Abbeel, and Sergey Levine. Reinforcement learn- ing with deep energy-based policies. In ICML, 2017.","title":"Reinforcement learning with deep energy-based policies","authors":"Tuomas Haarnoja, Haoran Tang, Pieter Abbeel, Sergey Levine","year":"2017","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Hong et al., 2018] Zhang-Wei Hong, Tzu-Yun Shann, Shih- Yang Su, Yi-Hsiang Chang, Tsu-Jui Fu, and Chun-Yi Lee. Diversity-driven exploration strategy for deep reinforce- ment learning. In NIPS, 2018.","title":"Diversity-driven exploration strategy for deep reinforcement learning","authors":"Zhang-Wei Hong, Tzu-Yun Shann, Shih-Yang Su, Yi-Hsiang Chang, Tsu-Jui Fu, Chun-Yi Lee","year":"2018","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Huynh and Mooney, 2008] Tuyen N. Huynh and Ray- mond J. Mooney. Discriminative structure and parameter learning for Markov logic networks. In ICML, 2008.","title":"Discriminative structure and parameter learning for Markov logic networks","authors":"N Tuyen, Raymond J Huynh, Mooney","year":"2008","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Huynh and Mooney, 2011] Tuyen N. Huynh and Ray- mond J. Mooney. Online structure learning for Markov logic networks. In ECML-PKDD, 2011.","title":"Online structure learning for Markov logic networks","authors":"N Tuyen, Raymond J Huynh, Mooney","year":"2011","venue":"ECML-PKDD","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Khosravi et al., 2010] Hassan Khosravi, Oliver Schulte, Tong Man, Xiaoyuan Xu, and Bahareh Bina. Structure learning for Markov logic networks with many descriptive attributes. In AAAI, 2010.","title":"Structure learning for Markov logic networks with many descriptive attributes","authors":"Hassan Khosravi, Oliver Schulte, Tong Man, Xiaoyuan Xu, Bahareh Bina","year":"2010","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Khot et al., 2011] Tushar Khot, Sriraam Natarajan, Kristian Kersting, and Jude Shavlik. Learning Markov logic net- works via functional gradient boosting. In ICDM, 2011.","title":"Learning Markov logic networks via functional gradient boosting","authors":"Tushar Khot, Sriraam Natarajan, Kristian Kersting, Jude Shavlik","year":"2011","venue":"ICDM","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Khot et al., 2015] Tushar Khot, Sriraam Natarajan, Kristian Kersting, and Jude Shavlik. Gradient-based boosting for statistical relational learning: the Markov logic network and missing data cases. Machine Learning, pages 75-100, 2015.","title":"Gradient-based boosting for statistical relational learning: the Markov logic network and missing data cases","authors":"Tushar Khot, Sriraam Natarajan, Kristian Kersting, Jude Shavlik","year":"2015","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Kok and Domingos, 2005] Stanley Kok and Pedro Domin- gos. Learning the structure of Markov logic networks. In ICML, 2005.","title":"Learning the structure of Markov logic networks","authors":"Domingos Kok, Stanley Kok, Pedro Domingos","year":"2005","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Kok and Domingos, 2009] Stanley Kok and Pedro Domin- gos. Learning Markov logic network structure via hyper- graph lifting. In ICML, 2009.","title":"Learning Markov logic network structure via hypergraph lifting","authors":"Domingos Kok, Stanley Kok, Pedro Domingos","year":"2009","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kok and Domingos, 2010] Stanley Kok and Pedro Domin- gos. Learning Markov logic networks using structural mo- tifs. In ICML, 2010.","title":"Learning Markov logic networks using structural motifs","authors":"Domingos Kok, Stanley Kok, Pedro Domingos","year":"2010","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Letham et al., 2015] Benjamin Letham, Cynthia Rudin, Tyler H McCormick, David Madigan, et al. Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model. The Annals of Applied Statistics, pages 1350-1371, 2015.","title":"Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model","authors":"Benjamin Letham, Cynthia Rudin, H Tyler, David Mccormick, Madigan","year":"2015","venue":"The Annals of Applied Statistics","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[McCallum, 2003] Andrew McCallum. Efficiently inducing features of conditional random fields. In UAI, 2003. [Mihalkova and Mooney, 2007] Lilyana Mihalkova and Raymond J. Mooney. Bottom-up learning of Markov logic network structure. In ICML, 2007.","title":"Efficiently inducing features of conditional random fields","authors":"Andrew Mccallum","year":"2003","venue":"UAI","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Mnih et al., 2016] Volodymyr Mnih, Adria Puigdomenech Badia, Mehdi Mirza, Alex Graves, Timothy Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu. Asyn- chronous methods for deep reinforcement learning. In ICML, 2016.","title":"Asynchronous methods for deep reinforcement learning","authors":"Volodymyr Mnih, Adria Puigdomenech Badia, Mehdi Mirza, Alex Graves, Timothy Lillicrap, Tim Harley, David Silver, Koray Kavukcuoglu","year":"2016","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Richardson and Domingos, 2006] Matthew Richardson and Pedro Domingos. Markov logic networks. Machine learn- ing, pages 107-136, 2006.","title":"Matthew Richardson and Pedro Domingos. Markov logic networks","authors":"Domingos Richardson","year":"2006","venue":"Machine learning","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Ross et al., 2017] Andrew Slavin Ross, Michael C. Hughes, and Finale Doshi-Velez. Right for the right reasons: Train- ing differentiable models by constraining their explana- tions. In IJCAI, 2017.","title":"Right for the right reasons: Training differentiable models by constraining their explanations","authors":"Andrew Slavin Ross, Michael C Hughes, Finale Doshi-Velez","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/371"},{"position":20,"raw":"[Tomkins et al., 2018] Sabina Tomkins, Lise Getoor, Yunfei Chen, and Yi Zhang. A socio-linguistic model for cyber- bullying detection. In ASONAM, 2018.","title":"A socio-linguistic model for cyberbullying detection","authors":"Sabina Tomkins, Lise Getoor, Yunfei Chen, Yi Zhang","year":"2018","venue":"ASONAM","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Wang and Cohen, 2016] William Yang Wang and William W Cohen. Learning first-order logic embeddings via matrix factorization. In IJCAI, 2016.","title":"Learning first-order logic embeddings via matrix factorization","authors":"William Yang, Wang, William W Cohen","year":"2016","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2016/304"},{"position":22,"raw":"[Wang et al., 2015] Tong Wang, Cynthia Rudin, Finale Doshi-Velez, Yimin Liu, Erica Klampfl, and Perry Mac- Neille. Or's of and's for interpretable classification, with application to context-aware recommender systems. arXiv:1504.07614, 2015.","title":"Or's of and's for interpretable classification, with application to context-aware recommender systems","authors":"Tong Wang, Cynthia Rudin, Finale Doshi-Velez, Yimin Liu, Erica Klampfl, Perry Mac-Neille","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wang et al., 2017a] Tong Wang, Cynthia Rudin, Finale Doshi-Velez, Yimin Liu, Erica Klampfl, and Perry Mac- Neille. A Bayesian framework for learning rule sets for in- terpretable classification. JMLR, pages 2357-2393, 2017.","title":"A Bayesian framework for learning rule sets for interpretable classification","authors":"Wang","year":"2017","venue":"JMLR","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Wang et al., 2017b] Ziyu Wang, Josh S Merel, Scott E Reed, Nando de Freitas, Gregory Wayne, and Nicolas Heess. Robust imitation of diverse behaviors. In NIPS, 2017.","title":"Robust imitation of diverse behaviors","authors":"Wang","year":"2017","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Zeng et al., 2014] Qiang Zeng, Jignesh M Patel, and David Page. Quickfoil: Scalable inductive logic programming. VLDB Endowment, 8(3):197-208, 2014.","title":"Quickfoil: Scalable inductive logic programming","authors":"Qiang Zeng, Jignesh M Patel, David Page","year":"2014","venue":"VLDB Endowment","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zhang and Ramesh, 2018] Yue Zhang and Arti Ramesh. Fine-grained analysis of cyberbullying using weakly- supervised topic models. In DSAA, 2018.","title":"Fine-grained analysis of cyberbullying using weaklysupervised topic models","authors":"Yue Zhang, Arti Ramesh","year":"2018","venue":"DSAA","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Zhang et al., 2018] Yue Zhang, Arti Ramesh, Jennifer Gol- beck, Dhanya Sridhar, and Lise Getoor. A structured ap- proach to understanding recovery and relapse in AA. In WWW, 2018.","title":"A structured approach to understanding recovery and relapse in AA","authors":"Yue Zhang, Arti Ramesh, Jennifer Golbeck, Dhanya Sridhar, Lise Getoor","year":"2018","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zhu et al., 2010] Jun Zhu, Ni Lao, and Eric P Xing. Grafting-light: fast, incremental feature selection and structure learning of Markov random fields. In SIGKDD, 2010.","title":"Grafting-light: fast, incremental feature selection and structure learning of Markov random fields","authors":"Jun Zhu, Ni Lao, Eric P Xing","year":"2010","venue":"SIGKDD","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}